Borrowing it
Nothing to install: this file belongs to ibm-granite/granite.build. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ibm-granite/granite.build/main/.claude/skills/run-gbserver/SKILL.mdgit clone --depth 1 https://github.com/ibm-granite/granite.buildWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ibm-granite/granite.build/run-gbserver)<a href="https://agentmods.dev/skills/ibm-granite/granite.build/run-gbserver"><img src="https://agentmods.dev/badge/skills/ibm-granite/granite.build/run-gbserver/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ibm-granite/granite.build/run-gbserver"><img src="https://agentmods.dev/badge/skills/ibm-granite/granite.build/run-gbserver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00963 |
| Opus 5 | $0.00023 | $0.00481 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
run-gbserver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensure the gbserver backend is up
The mcp__gbmcp__* tools run as a local stdio process that Claude Code launches, so they're always available. But the build tools (build_start, …) call a separate gbserver backend over REST — that process is what needs to be running. Manage it entirely through tools:
- Check:
gbserver_status()→ready: truemeans the backend is up; go run builds. - Start: if not ready,
gbserver_start()— launchesgbserver standaloneand blocks until reachable (idempotent; safe to call anytime). Returnsready: true, or anerror/log_tailif it couldn't start. - Stop:
gbserver_stop()— only when the user asks (see Lifecycle below).
The loop: gbserver_status → gbserver_start if needed → drive builds. No server to start by hand, and no endpoint to register.
Lifecycle — a long-lived dev service; leave it running
gbserver standalone is more than a build backend — the same process serves the web dashboard (http://127.0.0.1:<port>, the port from gbserver_status) and the REST/analytics API. Treat it like a dev server, not a per-build worker:
- Leave it running after a build finishes. The user likely wants to view the build and its result in the dashboard, and the next build reuses the warm server. After starting it, tell the user the dashboard URL so they can browse builds between runs.
- When you wrap up, hand the stop decision to the user. Tell them gbserver is still running and give the dashboard URL (from
gbserver_status), and ask them to let you know when they'd like it stopped. Don't phrase it as "should I stop it now?" (that frames stopping as expected), and nevergbserver_stopunprompted — leave it up until they ask. - It's a detached daemon, so it persists across sessions until stopped or a reboot (fine for a dev service). If the user wants a clean slate,
gbserver_stop.
Port already in use
If gbserver_status / gbserver_start reports the port is held by another (non-gbserver) process, gbserver can't bind it. The port is fixed at MCP-server launch, so it can't change mid-session — the user must exit and relaunch with a free port set, e.g. GBSERVER_PORT=<free> claude. Don't suggest ! … claude: the ! prefix runs inside the session, so it can't relaunch it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 41 lines · 46 tokens per session scan A 945d01412a34
run-gbserver is a skill published in the GitHub repository ibm-granite/granite.build (44 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 963 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…